{"id":18594183,"url":"https://github.com/rubenszimbres/repo-2022","last_synced_at":"2025-04-10T16:30:58.658Z","repository":{"id":37252328,"uuid":"487975460","full_name":"RubensZimbres/Repo-2022","owner":"RubensZimbres","description":"Python codes on PyTorch, Tensorflow, Keras, Wav2Vec2 Fine-Tuning and Google Cloud","archived":false,"fork":false,"pushed_at":"2023-09-10T19:01:38.000Z","size":78361,"stargazers_count":7,"open_issues_count":0,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-03-25T00:41:51.244Z","etag":null,"topics":["googlecloudplatform","keras-tensorflow","wav2vec2"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RubensZimbres.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-05-02T20:04:09.000Z","updated_at":"2024-01-05T13:14:29.000Z","dependencies_parsed_at":"2023-01-30T20:00:35.601Z","dependency_job_id":null,"html_url":"https://github.com/RubensZimbres/Repo-2022","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FRepo-2022","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FRepo-2022/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FRepo-2022/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FRepo-2022/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RubensZimbres","download_url":"https://codeload.github.com/RubensZimbres/Repo-2022/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248252690,"owners_count":21072700,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["googlecloudplatform","keras-tensorflow","wav2vec2"],"created_at":"2024-11-07T01:14:42.642Z","updated_at":"2025-04-10T16:30:53.643Z","avatar_url":"https://github.com/RubensZimbres.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Repo-2022  \n  \n\u003cb\u003eCellular Automaton\u003c/b\u003e  \nIn this Python file, I add a cellular automaton to a PyTorch kernel, add a residual layer to achieve 99.29% accuracy on test set in MNIST, results better than Robust Training in High Dimensions via Block Coordinate Geometric Median Descent\", by Google AI and Amazon Search (2021).\n  \n\u003cb\u003eTF-Keras\u003c/b\u003e  \nThis folder has the code to customize ResNet Architecture via dictionary config, changing first two layers to receive multispectral images with 9 channels. Final layers are also added, for training and inference.  \n  \n\u003cb\u003eSanta Fe\u003c/b\u003e  \nThis folder has the python code to create Agent-Based Models based in 2 and 5 state cellular automata.  \n\n\u003cimg src=https://github.com/RubensZimbres/Repo-2022/blob/main/png/MBA_github_noise_movie.gif\u003e\n\n\u003cimg src=https://github.com/RubensZimbres/Repo-2022/blob/main/SantaFe/NetLogo/NETLOGO_28.png\u003e\n\n\u003cb\u003eTensorflow Hub\u003c/b\u003e  \nThis folder has the code to generate word embeddings using BERT multilingual model from Tensorflow Hub, in the shape (2,768).  \n  \n\u003cb\u003eWav2Vec\u003c/b\u003e  \nHere you can find Python code to finetune Wav2Vec model (300 MB) of Speech Recognition on Common Voice dataset, as well as the code for evaluating the model. \n  \n\u003cb\u003eWav2Vec2-Large-xlsr\u003c/b\u003e  \nThese files allow the training of Facebook's Wav2Vec2-Large-xlsr (model 1.5 GB) on Common Voice dataset on a RTX 2060. Some layers are frozen to allow fit in the GPU. Paper available at: \u003ca href=\"url\"\u003ehttps://arxiv.org/abs/2006.11477\u003c/a\u003e. A pretrained version of the model is at my Hugging Face repository - Rubens Zimbres: \n\u003ca href=\"url\"\u003ehttps://huggingface.co/Rubens/Wav2Vec2-Large-XLSR-53-a-Portuguese\u003c/a\u003e  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frubenszimbres%2Frepo-2022","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frubenszimbres%2Frepo-2022","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frubenszimbres%2Frepo-2022/lists"}